high performance computing on graphics processing units: hgpu.org

This workshop will cover advances and innovations in graphic processor unit (GPU) capabilities and functionality into nontraditional, general-purpose computing as an adjunct vector/matrix processor. Examples include game physics, image processing, scientific computing, sorting and database query processing, to name a few.This workshop consists of invited speakers and poster presenters who provide insights into GP2 practice and experience gained over the last several years. Both perspectives are crucial to understanding upcoming and future heterogeneous and homogeneous multi-core processor architectures. Developing and adapting software to exploit the GPU’s embarassingly parallel capabilities presented numerous implementation challenges, resulting in a variety of approaches to integrating an attached processor with a CPU to achieve high problem throughput. Similar software development and integration challenges face the multi-core processor future, building on the GP2 foundation.